中文
相关论文

相关论文: The Dynamics of Gradient Descent for Overparametri…

200 篇论文

Neural networks, a central tool in machine learning, have demonstrated remarkable, high fidelity performance on image recognition and classification tasks. These successes evince an ability to accurately represent high dimensional…

机器学习 · 统计学 2023-02-08 Grant M. Rotskoff , Eric Vanden-Eijnden

The classical statistical learning theory implies that fitting too many parameters leads to overfitting and poor performance. That modern deep neural networks generalize well despite a large number of parameters contradicts this finding and…

机器学习 · 统计学 2022-10-18 Masaaki Imaizumi , Johannes Schmidt-Hieber

Understanding the advantages of deep neural networks trained by gradient descent (GD) compared to shallow models remains an open theoretical challenge. In this paper, we introduce a class of target functions (single and multi-index Gaussian…

机器学习 · 统计学 2025-11-17 Yatin Dandi , Luca Pesce , Lenka Zdeborová , Florent Krzakala

Recent research in neural networks and machine learning suggests that using many more parameters than strictly required by the initial complexity of a regression problem can result in more accurate or faster-converging models -- contrary to…

机器学习 · 计算机科学 2023-05-18 Arthur Castello B. de Oliveira , Milad Siami , Eduardo D. Sontag

This work focuses on the behavior of stochastic gradient descent (SGD) in solving least-squares regression with physics-informed neural networks (PINNs). Past work on this topic has been based on the over-parameterization regime, whose…

机器学习 · 计算机科学 2025-07-23 Zhihan Zeng , Yiqi Gu

Stochastic gradient descent (SGD) is widely believed to perform implicit regularization when used to train deep neural networks, but the precise manner in which this occurs has thus far been elusive. We prove that SGD minimizes an average…

机器学习 · 计算机科学 2018-01-17 Pratik Chaudhari , Stefano Soatto

We analyze speed of convergence to global optimum for gradient descent training a deep linear neural network (parameterized as $x \mapsto W_N W_{N-1} \cdots W_1 x$) by minimizing the $\ell_2$ loss over whitened data. Convergence at a linear…

机器学习 · 计算机科学 2019-10-29 Sanjeev Arora , Nadav Cohen , Noah Golowich , Wei Hu

We revisit the problem of learning a single neuron with ReLU activation under Gaussian input with square loss. We particularly focus on the over-parameterization setting where the student network has $n\ge 2$ neurons. We prove the global…

机器学习 · 计算机科学 2023-10-11 Weihang Xu , Simon S. Du

This work studies the global convergence and implicit bias of Gauss Newton's (GN) when optimizing over-parameterized one-hidden layer networks in the mean-field regime. We first establish a global convergence result for GN in the…

机器学习 · 计算机科学 2023-12-13 Michael Arbel , Romain Menegaux , Pierre Wolinski

A numerical and phenomenological study of the gradient descent (GD) algorithm for training two-layer neural network models is carried out for different parameter regimes when the target function can be accurately approximated by a…

机器学习 · 计算机科学 2020-06-26 Chao Ma , Lei Wu , Weinan E

Implicit deep learning has recently become popular in the machine learning community since these implicit models can achieve competitive performance with state-of-the-art deep networks while using significantly less memory and computational…

机器学习 · 计算机科学 2022-05-17 Tianxiang Gao , Hongyang Gao

Neural networks are usually trained by some form of stochastic gradient descent (SGD)). A number of strategies are in common use intended to improve SGD optimization, such as learning rate schedules, momentum, and batching. These are…

神经与进化计算 · 计算机科学 2015-08-13 Thomas M. Breuel

Multi-layer neural networks are among the most powerful models in machine learning, yet the fundamental reasons for this success defy mathematical understanding. Learning a neural network requires to optimize a non-convex high-dimensional…

机器学习 · 统计学 2022-06-08 Song Mei , Andrea Montanari , Phan-Minh Nguyen

We study the overparametrization bounds required for the global convergence of stochastic gradient descent algorithm for a class of one hidden layer feed-forward neural networks, considering most of the activation functions used in…

机器学习 · 计算机科学 2022-11-17 Bartłomiej Polaczyk , Jacek Cyranka

Neural networks are trained by optimizing multi-dimensional sets of fitting parameters on non-convex loss landscapes. Low-loss regions of the landscapes correspond to the parameter sets that perform well on the training data. A key issue in…

机器学习 · 计算机科学 2026-02-26 Jianneng Yu , Alexandre V. Morozov

The theory of training deep networks has become a central question of modern machine learning and has inspired many practical advancements. In particular, the gradient descent (GD) optimization algorithm has been extensively studied in…

最优化与控制 · 数学 2025-10-29 Alexandru Crăciun , Debarghya Ghoshdastidar

We prove linear convergence of gradient descent to a global optimum for the training of deep residual networks with constant layer width and smooth activation function. We show that if the trained weights, as a function of the layer index,…

机器学习 · 计算机科学 2023-01-26 Rama Cont , Alain Rossier , RenYuan Xu

Understanding the implicit bias of training algorithms is of crucial importance in order to explain the success of overparametrised neural networks. In this paper, we study the dynamics of stochastic gradient descent over diagonal linear…

机器学习 · 计算机科学 2021-12-08 Scott Pesme , Loucas Pillaud-Vivien , Nicolas Flammarion

This work analyzes the solution trajectory of gradient-based algorithms via a novel basis function decomposition. We show that, although solution trajectories of gradient-based algorithms may vary depending on the learning task, they behave…

机器学习 · 计算机科学 2022-10-05 Jianhao Ma , Lingjun Guo , Salar Fattahi

The training of machine learning models is typically carried out using some form of gradient descent, often with great success. However, non-asymptotic analyses of first-order optimization algorithms typically employ a gradient smoothness…

机器学习 · 计算机科学 2024-06-18 Thomas Flynn